Dispatch coding agents from GitHub issue labels and return pull requests with Patchwork Agents
Use issue labels as a lightweight dispatch layer that fans repository work out to Claude Code, Codex, or Aider workers and brings back PRs.
What it does
Dispatch coding agents from GitHub issue labels and return pull requests with Patchwork Agents
Use issue labels as a lightweight dispatch layer that fans repository work out to Claude Code, Codex, or Aider workers and brings back PRs.
Prerequisites
GitHub App or webhook setup, Kubernetes or k3s environment, supported coding-agent credentials, repository access, Patchwork Agents deployment
Installation
Use the upstream install or setup path that matches your environment:
- docker build -f images/orchestrator/Dockerfile -t ghcr.io/<your-org>/orchestrator:latest .
- docker save ghcr.io/<your-org>/orchestrator:latest | sudo k3s ctr images import -
- docker build -f images/worker-claude/Dockerfile -t worker-claude:latest .
- docker save worker-claude:latest | sudo k3s ctr images import -
Requirements and caveats from upstream:
- Tested on: VPS / 8 GB RAM / 4 vCPU / k3s single-node.
-
1. Prerequisites
- Manual option: k3s, Docker, and kubectl installed on the VPS
Basic usage or getting-started notes:
-
A VPS (or machine) with 4 vCPU / 8 GB RAM minimum
-
API keys for your desired AI worker providers
-
Ansible option: ansible installed locally + SSH root access to the VPS
-
Extracted from upstream docs: https://raw.githubusercontent.com/hey-intent/patchwork-agents/HEAD/README.md
Documentation
Source
Capabilities
Install
Quality
deterministic score 0.45 from registry signals: · indexed on github topic:agent-skills · 8 github stars · SKILL.md body (1,616 chars)